Beyond infancy, most Australian children are experiencing at least one ongoing health condition at any given time. This study's age-specific estimates of prevalence and persistence should assist families and clinicians to plan care. Conditions showing little resolution (obesity, asthma, attention-deficit hyperactivity disorder) require long-term planning and management.

Readily available baseline information (child/maternal BMI, maternal age, education and child health) were the strongest predictors of both onset and resolution of overweight/obesity between the primary school and adolescent years. Perinatal, breastfeeding and lifestyle exposures were not strongly predictive. Results could stimulate development of algorithms identifying children most in need of targeted prevention or treatment.

Purpose The purpose of this study was to develop a deep learning model for automatic binarization of the choroidal tissue, separating choroidal blood vessels from nonvascular stromal tissue, in optical coherence tomography (OCT) images from healthy young subjects. Methods OCT images from an observational longitudinal study of 100 children were used for training, validation, and testing of 5 fully semantic networks, which provided a binarized output of the choroid. These outputs were compared with ground truth images, generated from a local binarization technique after manually optimizing the analysis window size for each individual image. The performance was evaluated using accuracy and repeatability metrics. The methods were also compared with a fixed window size local binarization technique, which has been commonly used previously. Results The tested deep learning methods provided a good performance in terms of accuracy and repeatability. With the U-Net and SegNet networks showing >96% accuracy. All methods displayed a high level of repeatability relative to the ground truth. For analysis of the choroidal vascularity index (a commonly used metric derived from the binarized image), SegNet showed the closest agreement with the ground truth and high repeatability. The fixed window size showed a reduced accuracy compared to other methods. Conclusions Fully semantic networks such as U-Net and SegNet displayed excellent performance for the binarization task. These methods provide a useful approach for clinical and research applications of deep learning tools for the binarization of the choroid in OCT images. Translational Relevance Deep learning models provide a novel, robust solution to automatically binarize the choroidal tissue in OCT images.

Many endangered species exist in only a single population, and almost all species that go extinct will do so from their last remaining population. Understanding how to best conserve these single population threatened species (SPTS) is therefore a distinct and important task for threatened species conservation science. As a last resort, managers of SPTS may consider taking the entire population into captivity – ex situ, in toto conservation. In the past, this choice has been taken to the great benefit of the SPTS, but it has also lead to catastrophe. Here, we develop a decision-support tool for planning when to trigger this difficult action. Our method considers the uncertain and ongoing decline of the SPTS, the possibility that drastic ex situ action will fail, and the opportunities offered by delaying the decision. Specifically, these benefits are additional time for ongoing in situ actions to succeed, and opportunities for the managers to learn about the system. To illustrate its utility, we apply the decision tool to four retrospective case-studies of declining SPTS. As well as offering support to this particular decision, our tool illustrates why trigger points for difficult conservation decisions should be formulated in advance, but must also be adaptive. A trigger-point for the ex situ, in toto conservation of a SPTS, for example, will not take the form of a simple threshold abundance.

No abstract